Instructions to use mradermacher/Behemoth-3B-070225-post0.1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/Behemoth-3B-070225-post0.1-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/Behemoth-3B-070225-post0.1-GGUF", dtype="auto")

llama-cpp-python

How to use mradermacher/Behemoth-3B-070225-post0.1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mradermacher/Behemoth-3B-070225-post0.1-GGUF",
	filename="Behemoth-3B-070225-post0.1.IQ4_XS.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use mradermacher/Behemoth-3B-070225-post0.1-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mradermacher/Behemoth-3B-070225-post0.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/Behemoth-3B-070225-post0.1-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mradermacher/Behemoth-3B-070225-post0.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/Behemoth-3B-070225-post0.1-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf mradermacher/Behemoth-3B-070225-post0.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/Behemoth-3B-070225-post0.1-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf mradermacher/Behemoth-3B-070225-post0.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/Behemoth-3B-070225-post0.1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/Behemoth-3B-070225-post0.1-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/Behemoth-3B-070225-post0.1-GGUF with Ollama:
```
ollama run hf.co/mradermacher/Behemoth-3B-070225-post0.1-GGUF:Q4_K_M
```

Unsloth Studio

How to use mradermacher/Behemoth-3B-070225-post0.1-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mradermacher/Behemoth-3B-070225-post0.1-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mradermacher/Behemoth-3B-070225-post0.1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mradermacher/Behemoth-3B-070225-post0.1-GGUF to start chatting

Docker Model Runner
How to use mradermacher/Behemoth-3B-070225-post0.1-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/Behemoth-3B-070225-post0.1-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/Behemoth-3B-070225-post0.1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/Behemoth-3B-070225-post0.1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Behemoth-3B-070225-post0.1-GGUF-Q4_K_M

List all available models

lemonade list

mradermacher commited on Jul 2, 2025

Commit

f072b52

verified ·

1 Parent(s): 3d8ad6d

uploaded from nico1

Browse files

Files changed (13) hide show

.gitattributes +12 -0
Behemoth-3B-070225-post0.1.IQ4_XS.gguf +3 -0
Behemoth-3B-070225-post0.1.Q2_K.gguf +3 -0
Behemoth-3B-070225-post0.1.Q3_K_L.gguf +3 -0
Behemoth-3B-070225-post0.1.Q3_K_M.gguf +3 -0
Behemoth-3B-070225-post0.1.Q3_K_S.gguf +3 -0
Behemoth-3B-070225-post0.1.Q4_K_M.gguf +3 -0
Behemoth-3B-070225-post0.1.Q4_K_S.gguf +3 -0
Behemoth-3B-070225-post0.1.Q5_K_M.gguf +3 -0
Behemoth-3B-070225-post0.1.Q5_K_S.gguf +3 -0
Behemoth-3B-070225-post0.1.Q6_K.gguf +3 -0
Behemoth-3B-070225-post0.1.Q8_0.gguf +3 -0
Behemoth-3B-070225-post0.1.f16.gguf +3 -0

@@ -35,3 +35,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 Behemoth-3B-070225-post0.1.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 Behemoth-3B-070225-post0.1.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text

 *tfevents* filter=lfs diff=lfs merge=lfs -text
 Behemoth-3B-070225-post0.1.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 Behemoth-3B-070225-post0.1.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text
+Behemoth-3B-070225-post0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Behemoth-3B-070225-post0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Behemoth-3B-070225-post0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Behemoth-3B-070225-post0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Behemoth-3B-070225-post0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Behemoth-3B-070225-post0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Behemoth-3B-070225-post0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Behemoth-3B-070225-post0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Behemoth-3B-070225-post0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Behemoth-3B-070225-post0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Behemoth-3B-070225-post0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Behemoth-3B-070225-post0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:98ab506b8957d3eb1a75ead02c21ea8a7ff1f382179006591b28dd3c6428be24
+size 1753183872

+version https://git-lfs.github.com/spec/v1
+oid sha256:d3c8a677683ab9bd68a7a4212288984ff44e9a103911727ad3f006b20638c235
+size 1274754688

+version https://git-lfs.github.com/spec/v1
+oid sha256:689c8f9f4ac038a21e029fd744c63fc077a7ccf59c99225dac4d4f6c424e1fb2
+size 1707390592

+version https://git-lfs.github.com/spec/v1
+oid sha256:41f5f1fa61e6a7a2eb400a75f3cb04acf6248635d9b03c4c6b35364cb8b1a80c
+size 1590474368

+version https://git-lfs.github.com/spec/v1
+oid sha256:d64adcdf268f4c5d7e3cd2d3c632d37f6c69fca3e66486b748893f644d1da3bf
+size 1454356096

+version https://git-lfs.github.com/spec/v1
+oid sha256:e84d96b622b4de36b4dec9c3a32da773301f1bb0212c449c818021087ad26d18
+size 1929901696

+version https://git-lfs.github.com/spec/v1
+oid sha256:fbd2531704688f09fd645e0d53b675b203488012399e65742afe90f3456b1ac6
+size 1834382976

+version https://git-lfs.github.com/spec/v1
+oid sha256:42f6f337323b0247dbc2c7ddac6e0a7817dbe791a48a3d309aa9aa8160aff78d
+size 2224813696

+version https://git-lfs.github.com/spec/v1
+oid sha256:912290b0fafabd64a62713b3a51a4600dffd868082bdd7ac87b51cb3364aa2df
+size 2169665152

+version https://git-lfs.github.com/spec/v1
+oid sha256:da29b35723a9084b874eae4319a6422f0d97bc2171e168a7ed0b2d5a40d60e7c
+size 2538157696

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:72dcc12545b876553e5319dbbb16007dcb4da415a6bfccaf95ea91c76cf1122a
+size 3285474944

+version https://git-lfs.github.com/spec/v1
+oid sha256:e10a31acf9a419a8a9d60ea0247f3d7b523c135957f1a0f8762751b0d87413ae
+size 6178315904